Class Weighted Focal Loss for Improving Class Imbalance in Semi-Supervised Object Detection

Shinichi Hoketsu, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

2024

Abstract

Object detection is a task for acquiring environmental information in automated driving. Object detection is used to detect the position and class of objects in an image. It can be made more accurate by learning with a large amount of supervised data. However, the high cost of annotating the data makes it difficult to create large supervised datasets. Therefore, research using semi-supervised learning for object detection has been attracting attention. Previous studies on semi-supervised learning in object detection tasks have mainly conducted evaluation experiments only on large datasets with many classes, such as MS COCO, and PASCAL VOC. Therefore, the effectiveness of semi-supervised learning for in-vehicle camera data as input has not yet been demonstrated. We examined the effectiveness of semi-supervised learning in object detection when in-vehicle camera data are used as input. We also proposed a class weighted focal loss that employs a unique weighting method that takes into account the class imbalance problem. Experimental results indicate that semi-supervised learning is also effective when vehicle-mounted camera images are used as input. We also confirmed that the proposed mitigates improves the class imbalance problem and improves accuracy.

Paper Citation

in Harvard Style

Hoketsu S., Hirakawa T., Yamashita T. and Fujiyoshi H. (2024). Class Weighted Focal Loss for Improving Class Imbalance in Semi-Supervised Object Detection. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 417-424. DOI: 10.5220/0012351600003660

in Bibtex Style

@conference{visapp24,
author={Shinichi Hoketsu and Tsubasa Hirakawa and Takayoshi Yamashita and Hironobu Fujiyoshi},
title={Class Weighted Focal Loss for Improving Class Imbalance in Semi-Supervised Object Detection},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={417-424},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012351600003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Class Weighted Focal Loss for Improving Class Imbalance in Semi-Supervised Object Detection
SN - 978-989-758-679-8
AU - Hoketsu S.
AU - Hirakawa T.
AU - Yamashita T.
AU - Fujiyoshi H.
PY - 2024
SP - 417
EP - 424
DO - 10.5220/0012351600003660
PB - SciTePress